All posts by choosehappy

Efficient pixel-wise deep learning on large images

This blog post is based on the net surgery example provided by Caffe. It takes the concept and expands it to a working example to produce pixel-wise output images, generating output in ~2 seconds (simple approach) or ~35 seconds (advanced approach) for a 2,000 x 2,000 image, an improvement from the  ~15 hours of a naive pixel wise approach.

Continue reading Efficient pixel-wise deep learning on large images

Use Case 6: Invasive Ductal Carcinoma (IDC) Segmentation

This blog posts explains how to train a deep learning Invasive Ductal Carcinoma (IDC) classifier in accordance with our paper “Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases”.

Continue reading Use Case 6: Invasive Ductal Carcinoma (IDC) Segmentation

Use Case 4: Lymphocyte Detection

Typically, you’ll want to use a validation set to determine an optimal threshold as it is often not .5 (which is equivalent to argmax). Subsequently, use this threshold on the the “_prob” image to generate a binary image.This blog posts explains how to train a deep learning lymphocyte detector in accordance with our paper “Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases”.

Continue reading Use Case 4: Lymphocyte Detection

Exporting from Matlab To PowerPoint

Reviewing the results of an image based experiment, across many images, can be annoying in matlab. Too much clicking!

I’ve recently started using PowerPoint to view many of my results. This blog posts discuss how using the free export to PowerPoint toolbox it is possible to create a slide desk with all relevant information for easier viewing. It looks like this:


image1_annotated_trimmed

Continue reading Exporting from Matlab To PowerPoint